The single domain generalization(SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem. However, the inadequate match of data distribution between source and augmented domains and difficult separation of domain-invariant features from domain-related features make SDG model hard to achieve great generalization. Therefore, a novel meta-learning method based on domain enhancement and feature alignment (MetaDefa) is proposed to improve the model generalization performance. First, the background substitution and visual corruptions techniques are used to generate diverse and effective augmented domains. Then, the multi-channel feature alignment module based on class activation maps and class agnostic activation maps is designed to effectively extract adequate transferability knowledge. In this module, domain-invariant features can be fully explored by focusing on similar target regions between source and augmented domains feature space and suppressing the feature representation of non-similar target regions. Extensive experiments on two publicly available datasets show that MetaDefa has significant generalization performance advantages in unknown multiple target domains.

翻译：摘要：基于元学习的单域泛化(SDG)已成为解决域偏移问题的有效技术。然而，源域与增强域之间数据分布的不充分匹配，以及域不变特征与域相关特征的难以分离，使得SDG模型难以实现良好的泛化性能。为此，本文提出了一种基于域增强与特征对齐的新型元学习方法(MetaDefa)，旨在提升模型泛化性能。首先，采用背景替换与视觉损坏技术生成多样且有效的增强域。其次，设计了基于类激活图与类不可知激活图的多通道特征对齐模块，以有效提取充足的迁移性知识。该模块通过聚焦源域与增强域特征空间中相似目标区域，并抑制非相似目标区域的特征表示，可充分挖掘域不变特征。在两个公开数据集上的大量实验表明，MetaDefa在未知多个目标域上具有显著的泛化性能优势。